© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117297
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on long runs of whitespace characters (e.g. deep indentation or extensive space/tab sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    䛗
    -0.85
    Feeling
    -0.84
    tiller
    -0.84
    inhalt
    -0.84
    
    -0.82
     >&
    -0.81
    viel
    -0.81
    帮我
    -0.80
    på
    -0.79
    休闲
    -0.79
    POSITIVE LOGITS
     Because
    0.82
     While
    0.80
     Recently
    0.78
     Within
    0.78
     Bring
    0.76
    ₂)
    0.75
     behaup
    0.75
    mper
    0.75
     завжди
    0.74
    varlak
    0.74
    Activations Density 0.036%

    No Known Activations